The Holistic Storage of Verb+Up Phrases in Text-based and Audio-based Language Models
Not on the map. Why?
Abstract (arXiv)
One of the most central aspects of language processing is the ability to trade off between stored representations and abstract knowledge: one must retrieve stored representations, but also generate novel ones by applying productive rules. While recent work has examined abstract knowledge in language models, holistic storage has received far less attention. We probe internal representations in both text-based LLMs and an ASR model, testing whether V+up phrasal verbs develop distinct representations as a function of frequency and predictability. All models show evidence of holistic storage driven by frequency and predictability, further supporting usage-based theories of language.
Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 8 of its 32 references that are in the map. First posted on arXiv 12 Jun 2026.
Builds on
8 of 32 references.
References · 8
- 2019Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformercited by 14,491
- 2021GigaSpeech: An Evolving, Multi-domain ASR Corpus with 10,000 Hours of Transcribed Audiocited by 391
- 2024Infini-gram: Scaling Unbounded n-gram Language Models to a Trillion Tokenscited by 148
- 2021How much do language models copy from their training data? Evaluating linguistic novelty in text generation using RAVENcited by 124
- 2024Language Models Learn Rare Phenomena from Less Rare Phenomena: The Case of the Missing AANNscited by 65
- 2025Both Direct and Indirect Evidence Contribute to Dative Alternation Preferences in Language Modelscited by 18
- 2022Subject Verb Agreement Error Patterns in Meaningless Sentences: Humans vs. BERTcited by 6
- 2026On the Interpretability of Whisper Encodings Using Sparse Autoencoderscited by 1
Built on by
Not cited yet.